8 papers
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
Zhaochong An, Orest Kupyn, Théo Uscidda +5
Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting th…
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov +2
Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a kno…
Generalized Discrete Diffusion from Snapshots
Oussama Zekri, Théo Uscidda, Nicolas Boullé +1
We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete…
LATTS: Locally Adaptive Test-Time Scaling
Theo Uscidda, Matthew Trager, Michael Kleinman +3
One common strategy for improving the performance of Large Language Models (LLMs) on downstream tasks involves using a \emph{verifier model} to either select the best answer from a…
Disentangled Representation Learning with the Gromov-Monge Gap
Théo Uscidda, Luca Eyring, Karsten Roth +3
Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretab…
GeOT: A spatially explicit framework for evaluating spatio-temporal predictions
Nina Wiedemann, Théo Uscidda, Martin Raubal
When predicting observations across space and time, the spatial layout of errors impacts a model's real-world utility. For instance, in bike sharing demand prediction, error patter…